© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2373
    Prev
    Next
    INDEX
    Explanations

    components and properties related to typography and handwritten character recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens related to letters or characters

    np_acts-logits-general · gemini-2.0-flash

    characters and letter forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elemField
    -0.70
     transférez
    -0.64
     utafitiHapana
    -0.62
    protoimpl
    -0.61
     Signalez
    -0.60
     transfieras
    -0.59
     चीज़ों
    -0.58
    нгред
    -0.58
    oa̍t
    -0.57
    encodeWith
    -0.57
    POSITIVE LOGITS
     letters
    0.36
     letter
    0.35
     Tisch
    0.31
    em
    0.30
    Letter
    0.30
    letter
    0.29
    amey
    0.28
     snippetHide
    0.28
     nur
    0.28
     Letters
    0.28
    Activations Density 0.846%

    No Known Activations